INDEX

Explanations

numerical data or statistics related to financial or health metrics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

opus

-0.17

amac

-0.17

ebe

-0.16

sak

-0.14

collect

-0.14

ONGO

-0.14

à¸´à¸Ī

-0.14

 Rico

-0.14

ilities

-0.14

imes

-0.13

POSITIVE LOGITS

0.16

veh

0.15

 Rounded

0.15

Ø·Ùĩ

0.14

ìłĿ

0.14

Activations Density 0.376%

numerical data or statistics related to financial or health metrics

No Comments

No Known Activations